Conditional MoCoGAN for Zero-Shot Video Generation
This work addresses video generation for unseen classes, but it is incremental as it builds on existing motion-content GANs.
The authors tackled zero-shot video generation by learning disentangled representations in a GAN's latent space, achieving improved video quality on the Weizmann and MUG databases.
We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. In this study, we have explored zero-shot conditional generation setting. In other words, we generate unseen videos from training samples with missing classes. The task is an extension of conditional data generation. The key idea is to learn disentangled representations in the latent space of a GAN. To realize this objective, we base our model on the motion and content decomposed GAN and conditional GAN for image generation. We build the model to find better-disentangled representations and to generate good-quality videos. We demonstrate the effectiveness of our proposed model through experiments on the Weizmann action database and the MUG facial expression database.